Artificial Intelligence on Big Data for Mining Applications

1. Artificial Intelligence on Big Data for Mining Applications Applying Data Analytics and Artificial Intelligence(AI) Methods for Mining Efficiency Burcin Ozturk Demirhanoz – Sept 2016

2. Burcin Ozturk Demirhanoz has been in and working professionally in mining and equipment industry more than 14 years in Europe and in Australia. She has completed her BSc, Mining Engineering (ITU, Istanbul) and MEng, Mining Engineering, Mine Management and also Business Administration (UNSW, Sydney). She is currently working as a Principal Mining Applications and Performance Engineer at WesTrac CAT and leading mining applications performance management projects at Western Australia region for some of the biggest mining companies in the world. Her research interest are mining performance analysis and modelling applying AI (Artificial Intelligence) methodologies within data analytics and machine learning. Biography

3. Introduction • Mining Applications and Technology • Prospect Objectives • The Era is on Performance Intelligence • Data analytics and AI for Mining • Conclusions Content

4. In mining industry, efficient and cost effective project development is critical to be succeeded since it is long term business and also because of the global economic concerns needs new approaches more than before. Introduction

5. One of the serious tasks faced by observing and monitoring methodologies is to ally data science into detailed engineering. This will apply scientific hypothesis-testing approach, essentially not only optimizing the algorithms but also generating new hypothesis to monitor and to improve the efficiency. Introduction

6. Regardless of the mining booms, mining processes and systems has stayed traditional for a long time. Nowadays, Mining industry is trending for change not only to increase productivity performance, but also to monitor cost per tonne. Mining Applications and Technology

7. Above and beyond, today’s overall mining operations productivity is approximately 28 percent less than ten years ago considering the adjustment for declining ore grades. (McKinsey, 2015) Mining Applications and Technology

8. The potential to achieve growth through innovation is on the way that could alter even basic characteristics of mining applications and performance to advance. This approach will still create opportunities on big data to manage the mining applications and performance for future in an analytical manner. Mining Applications and Technology

9. Mining Projects are contingent on new investment decisions at the moment, which are linked to emerging technologies for performance management applying new methodologies such as machine learning, big data analytics and artificial intelligence etc. Mining Applications and Technology

10. Globally mining companies have been concentrating continuous improvements using new processes and systems such as Six Sigma Principles to eliminate the defects as much as possible for business management. At the leading edge, big data analytics will help automate decisions for real-time business processes for instance mining trucks are applying object detections in autonomy on real time. Mining Applications and Technology

11. In mining sector, especially primary organizations need to ever more emphasize continuous process improvement through –data driven decision making with predictive analytics. Research objective will be rethinking how mine operations works in specifics and analysing the big data to have zero defect scoring for higher efficiencies in production. Prospect Objectives

12. The research focus might be to demonstrate the potential for value by undertaking a number of case studies using data collected across a number of mining operations. Innovation could be available with new mining machine learning models as soon as it has been identified, then implementing new engineering algorithms and model solutions into mine applications more intelligently. Prospect Objectives

13. Projects are depending on new investment decisions nowadays, are in terms of innovative technology for mining applications and performance supervision. Applications are to importance on learning from the previous and calculating future performance with higher confidence on continuous and statistical analysis of operating data from varied sources. The Era is on Performance Intelligence

14. Artificial Intelligence will be one of the crucial element to compare both man fleets and autonomous fleets in mining, since it aims to achieve by foreseeing how movements will affect the model of the mine progress and production. The Era is on Performance Intelligence

15. It takes the actions that will greatest accomplish that job on real time intelligently. Support in the exclusion of defects; observing and assessing performance enhancements are key capacities for future intelligence. The Era is on Performance Intelligence

16. Modern wireless based management systems and applications for mining equipment fleets are capable of collecting vast amounts of equipment health and mining performance data. However, when performance and machine health deviates from desired target levels, it can sometime be difficult to determine the root cause. Data analytics and AI for Mining

17. This is because data relating to the operating environment or maintenance actions taken often reside in different data bases, applying different fields including database design, statistics, pattern recognition, machine learning, and data visualization. Data analytics and AI for Mining

18. The “silo” approach to data often inhibits the extent to which evidence-based root causes can be determined and generate cost modeling in advance due to actuals. These kind of research hypotheses that there is significant value to be had by integrating data from different sources and using this to determine and manage root cause of performance and equipment health problems in advance to start with. Conclusion

19. Big Data will be one of the main input to classify and monitor mining applications performance as well as the design of the mining production models. Specific algorithm's could be developed using Big Data to implement AI and machine learning solutions. Conclusion

20. THANK YOU